orchard

A command for managing several related software sprints and the dependencies between them. It reads an orchard.json file, which describes the sprints and their order.

In plain words
What is it for?
It displays a sprint dependency graph and lists ready sprints as JSON. It can also print the graph in Mermaid format, a text format for diagrams.
Why use it?
It shows which work is finished, active, blocked, or ready, so you do not have to track dependencies by hand. It also identifies the next sprints that can start.

Skill for Claude CodeCodex

Part of the grainulator plugin — 19 skills, 1 agent, 2 hooks, 4 MCP servers shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/grainulation/grainulator/orchard
Any agent
npx skills add grainulation/grainulator --skill orchard
Clone the repo
git clone --depth 1 https://github.com/grainulation/grainulator

Made for: Claude Code, Codex.

Or install grainulator, the plugin that ships this one along with the rest of its 19 skills, 1 agent, 2 hooks, 4 MCP servers.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 965 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00965
Opus 5 $0.00009 $0.00483
Sonnet 5 $0.00003 $0.00193
Haiku 4.5 $0.00002 $0.00097

Measured 3d ago against content hash 8a181fdabeb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/orchard/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/orchard -- Multi-sprint orchestration

View the sprint dependency graph, check sprint states, and dispatch the next ready sprint for execution.

Arguments

$ARGUMENTS

Instructions

Step 1: Locate orchard.json

Search for orchard.json in these locations (in order):

  1. Project root (current working directory)
  2. .wheat/ subdirectory

Use Glob to find it:

**/orchard.json

If found, read it and proceed to Step 2.

If NOT found, skip to Step 5.

Step 2: Show the dependency graph

Run:

npx @grainulation/orchard plan --format ascii

This prints the full sprint dependency graph with status indicators. Display the output as-is -- it already includes status markers (done, active, blocked, ready).

If the user passed arguments like --mermaid or --format mermaid, forward them:

npx @grainulation/orchard plan --mermaid

Step 3: Get next ready sprints

Run:

npx @grainulation/orchard next --json

This returns a JSON array of sprints whose dependencies are satisfied and are ready for execution. Parse the output.

If the command fails (e.g., all sprints are done or blocked), note that in the summary.

Step 4: Display actionable commands

For each ready sprint from Step 3, format it as a concrete command the user can run:

Ready sprints:
  /research "Sprint question here"   -- path: .wheat/sprints/sprint-slug
  /research "Another question"       -- path: .wheat/sprints/other-slug

Then print a summary:

Orchard: <total> sprints, <done> done, <active> active, <ready> ready, <blocked> blocked

Next steps:
  /research "<first ready sprint question>"  -- execute the next ready sprint
  /orchard                                   -- refresh after sprint completes
  orchard sync                               -- re-sync sprint states from directories

If no sprints are ready but some are blocked, explain which dependencies need to complete first.

If all sprints are done, congratulate and suggest:

Read the full file on GitHub · 145 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 145 lines · 17 tokens per session scan A 8a181fdabeb4

Subscribe to this mod's changes

orchard is a skill published in the GitHub repository grainulation/grainulator (86 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 965 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.